metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - template:sd-lora
  - standard
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      a lighthouse, sus4nm_style, bold clean shapes with refined, detailed
      accents, sharp contrasts for depth and shading
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

susanm_flux_lora

This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.

The main validation prompt used during training was:

a lighthouse, sus4nm_style, bold clean shapes with refined, detailed accents, sharp contrasts for depth and shading

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolution: 1024x1024

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

Prompt
unconditional (blank prompt)

Negative Prompt
blurry, cropped, ugly

Prompt
a lighthouse, sus4nm_style, bold clean shapes with refined, detailed accents, sharp contrasts for depth and shading

Negative Prompt
blurry, cropped, ugly

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

Training epochs: 499
Training steps: 10000
Learning rate: 0.0001
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
Precision: Pure BF16
Quantised: No
Xformers: Not used
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

paper_dataset

Repeats: 0
Total number of images: 20
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'vheretic/susanm_flux_lora'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "a lighthouse, sus4nm_style, bold clean shapes with refined, detailed accents, sharp contrasts for depth and shading"

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")